view src/os/unix/ngx_gcc_atomic_x86.h @ 160:73e8476f9142 NGINX_0_3_27

nginx 0.3.27 *) Change: the "variables_hash_max_size" and "variables_hash_bucket_size" directives. *) Feature: the $body_bytes_sent variable can be used not only in the "log_format" directive. *) Feature: the $ssl_protocol and $ssl_cipher variables. *) Feature: the cache line size detection for widespread CPUs at start time. *) Feature: now the "accept_mutex" directive is supported using fcntl(2) on platforms different from i386, amd64, sparc64, and ppc. *) Feature: the "lock_file" directive and the --with-lock-path=PATH autoconfiguration directive. *) Bugfix: if the HTTPS protocol was used in the "proxy_pass" directive then the requests with the body was not transferred.
author Igor Sysoev <http://sysoev.ru>
date Wed, 08 Feb 2006 00:00:00 +0300
parents 8e6d4d96ec4c
children 052a7b1d40e5
line wrap: on
line source


/*
 * Copyright (C) Igor Sysoev
 */


#if (NGX_SMP)
#define NGX_SMP_LOCK  "lock;"
#else
#define NGX_SMP_LOCK
#endif


/*
 * "cmpxchgl  r, [m]":
 *
 *     if (eax == [m]) {
 *         zf = 1;
 *         [m] = r;
 *     } else {
 *         zf = 0;
 *         eax = [m];
 *     }
 *
 *
 * The "q" is any of the %eax, %ebx, %ecx, or %edx registers.
 * The "=a" and "a" are the %eax register.  Although we can return result
 * in any register, we use %eax because it is used in cmpxchgl anyway.
 * The "cc" means that flags were changed.
 */

static ngx_inline ngx_atomic_uint_t
ngx_atomic_cmp_set(ngx_atomic_t *lock, ngx_atomic_uint_t old,
    ngx_atomic_uint_t set)
{
    ngx_atomic_uint_t  res;

    __asm__ volatile (

         NGX_SMP_LOCK
    "    cmpxchgl  %3, %1;   "
    "    setz      %b0;      "
    "    movzbl    %b0, %0;  "

    : "=a" (res) : "m" (*lock), "a" (old), "q" (set) : "cc", "memory");

    return res;
}


/*
 * "xaddl  r, [m]":
 *
 *     temp = [m];
 *     [m] += r;
 *     r = temp;
 *
 *
 * The "+q" is any of the %eax, %ebx, %ecx, or %edx registers.
 * The "cc" means that flags were changed.
 */


#if !(( __GNUC__ == 2 && __GNUC_MINOR__ <= 7 ) || ( __INTEL_COMPILER >= 800 ))

/*
 * icc 8.1 and 9.0 compile broken code with -march=pentium4 option:
 * ngx_atomic_fetch_add() always return the input "add" value,
 * so we use the gcc 2.7 version.
 *
 * icc 8.1 and 9.0 with -march=pentiumpro option or icc 7.1 compile
 * correct code.
 */

static ngx_inline ngx_atomic_int_t
ngx_atomic_fetch_add(ngx_atomic_t *value, ngx_atomic_int_t add)
{
    __asm__ volatile (

         NGX_SMP_LOCK
    "    xaddl  %0, %1;   "

    : "+q" (add) : "m" (*value) : "cc", "memory");

    return add;
}


#else

/*
 * gcc 2.7 does not support "+q", so we have to use the fixed %eax ("=a" and
 * "a") and this adds two superfluous instructions in the end of code,
 * something like this: "mov %eax, %edx / mov %edx, %eax".
 */

static ngx_inline ngx_atomic_int_t
ngx_atomic_fetch_add(ngx_atomic_t *value, ngx_atomic_int_t add)
{
    ngx_atomic_uint_t  old;

    __asm__ volatile (

         NGX_SMP_LOCK
    "    xaddl  %2, %1;   "

    : "=a" (old) : "m" (*value), "a" (add) : "cc", "memory");

    return old;
}

#endif


/*
 * on x86 the write operations go in a program order, so we need only
 * to disable the gcc reorder optimizations
 */

#define ngx_memory_barrier()    __asm__ volatile ("" ::: "memory")

/* old as does not support "pause" opcode */
#define ngx_cpu_pause()         __asm__ (".byte 0xf3, 0x90")